@tanstack/ai 0.53.0 → 0.55.0

package/skills/ai-core/adapter-configuration/references/openrouter-adapter.md

@@ -38,24 +38,29 @@ the format `provider/model-name`:
 OpenRouter has unique routing and provider selection options:
 
 ```typescript
+import { chat } from '@tanstack/ai'
+import { openRouterText } from '@tanstack/ai-openrouter'
+
+const messages = [{ role: 'user' as const, content: 'Hello' }]
+
+// Options are narrowed per model from OpenRouter's published metadata —
+// e.g. 'anthropic/claude-sonnet-4' only accepts temperature/topP/
+// maxCompletionTokens/stop/toolChoice/reasoning. This model takes the full set.
 chat({
-  adapter: openRouterText('anthropic/claude-sonnet-4'),
+  adapter: openRouterText('deepseek/deepseek-v4-pro'),
   messages,
   modelOptions: {
     // Reasoning
     reasoning: {
-      effort: 'high', // 'none' | 'minimal' | 'low' | 'medium' | 'high'
-      max_tokens: 4096,
-      exclude: false,
+      effort: 'high', // 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max'
+      summary: 'auto',
+      // enabled: false — explicit opt-out (normalized to effort: 'none')
     },
     // Sampling
     temperature: 0.7,
     topP: 0.9,
-    topK: 40,
     frequencyPenalty: 0.5,
     presencePenalty: 0.5,
-    repetitionPenalty: 1.1,
-    minP: 0.05,
     seed: 42,
     // Token limits
     maxCompletionTokens: 8192,
@@ -66,12 +71,11 @@ chat({
     parallelToolCalls: true,
     // Response format
     responseFormat: { type: 'json_object' },
-    // Web search
-    webSearchOptions: {
-      search_context_size: 'medium', // 'low' | 'medium' | 'high'
-    },
-    // Verbosity
-    verbosity: 'medium',
+    // Routing (available on every model)
+    variant: 'nitro', // 'free' | 'nitro' | 'online' | 'exacto' | 'extended' | 'thinking'
+    models: ['deepseek/deepseek-v4-flash'], // fallbacks, tried in order
+    provider: { order: ['DeepSeek'], allowFallbacks: true },
+    plugins: [{ id: 'web' }], // web search
     // Logprobs
     logprobs: true,
     topLogprobs: 5,
@@ -89,11 +93,20 @@ OPENROUTER_API_KEY
 
 - Model IDs are `provider/model-name` format (e.g., `openai/gpt-5.2`).
 - OpenRouter has unique features not found in direct provider adapters:
-  - `variant` option: `'free'`, `'nitro'`, `'online'`, `'thinking'`, etc.
-  - `provider` routing preferences (order, fallbacks, data collection policies)
-  - `transforms: ['middle-out']` for context compression
-  - `prediction` for latency reduction
-  - `plugins: [{ id: 'web' }]` for web search
-- Uses `camelCase` for option names (e.g., `topP`, `frequencyPenalty`),
-  unlike OpenAI's `snake_case`.
-- `route: 'fallback'` with `models` array tries models in order.
+  - `variant` option: `'free'`, `'nitro'`, `'online'`, `'exacto'`,
+    `'extended'`, `'thinking'`
+  - `provider` routing preferences (`order`, `allowFallbacks`, data
+    collection policies — camelCase keys)
+  - `models` array of fallback ids, tried in order
+  - `plugins: [{ id: 'web' }]` for web search (also `file-parser`,
+    `response-healing`, `moderation`, `auto-router`)
+- Uses `camelCase` for option names (e.g., `topP`, `frequencyPenalty`,
+  `maxCompletionTokens`), unlike OpenAI's `snake_case`.
+- `reasoning` is `{ effort, summary, enabled }` — there is no
+  `max_tokens`/`exclude` inside it; `enabled: false` is normalized to
+  `effort: 'none'`.
+- Per-model options are narrowed from OpenRouter's published metadata, so
+  keys like `frequencyPenalty`, `seed`, `logprobs`, or `responseFormat` are
+  only accepted on models that support them. `topK`, `minP`,
+  `repetitionPenalty`, `webSearchOptions`, `verbosity`, `transforms`, and
+  `route` are not exposed by the adapter.

package/skills/ai-core/ag-ui-protocol/SKILL.md

@@ -29,7 +29,7 @@ import { openaiText } from '@tanstack/ai-openai'
 export async function POST(request: Request) {
   const { messages } = await request.json()
   const stream = chat({
-    adapter: openaiText('gpt-5.2'),
+    adapter: openaiText('gpt-5.6'),
     messages,
   })
   return toServerSentEventsResponse(stream)
@@ -49,7 +49,7 @@ import {
   mergeAgentTools,
   toServerSentEventsResponse,
 } from '@tanstack/ai'
-import { openaiText } from '@tanstack/ai-openai/adapters'
+import { openaiText } from '@tanstack/ai-openai'
 import { serverTools } from './tools'
 
 export async function POST(req: Request) {
@@ -64,7 +64,7 @@ export async function POST(req: Request) {
   }
 
   const stream = chat({
-    adapter: openaiText('gpt-4o'),
+    adapter: openaiText('gpt-5.6'),
     messages: params.messages,
     tools: mergeAgentTools(serverTools, params.tools),
   })
@@ -87,7 +87,7 @@ export async function POST(req: Request) {
 
 **Wire format:** Each event is `data: <JSON>\n\n`. Stream ends with `data: [DONE]\n\n`.
 
-```typescript
+```typescript group=sse-response
 import {
   chat,
   toServerSentEventsStream,
@@ -95,10 +95,12 @@ import {
 } from '@tanstack/ai'
 import { openaiText } from '@tanstack/ai-openai'
 
+const messages = [{ role: 'user' as const, content: 'Hello' }]
+
 // Option A: Get a ReadableStream (manual Response construction)
 const abortController = new AbortController()
 const stream = chat({
-  adapter: openaiText('gpt-5.2'),
+  adapter: openaiText('gpt-5.6'),
   messages,
   abortController,
 })
@@ -127,7 +129,7 @@ const response2 = toServerSentEventsResponse(stream, { abortController })
 
 Custom headers merge on top (user headers override defaults):
 
-```typescript
+```typescript group=sse-response
 toServerSentEventsResponse(stream, {
   headers: {
     'X-Accel-Buffering': 'no', // Disable nginx buffering
@@ -149,10 +151,12 @@ aborted, the error event is suppressed and the stream closes silently.
 import { chat, toHttpStream, toHttpResponse } from '@tanstack/ai'
 import { openaiText } from '@tanstack/ai-openai'
 
+const messages = [{ role: 'user' as const, content: 'Hello' }]
+
 // Option A: Get a ReadableStream
 const abortController = new AbortController()
 const stream = chat({
-  adapter: openaiText('gpt-5.2'),
+  adapter: openaiText('gpt-5.6'),
   messages,
   abortController,
 })
@@ -199,7 +203,7 @@ All events extend `BaseAGUIEvent` which carries `type`, `timestamp`, optional
 | `STATE_DELTA`          | Incremental state update. Carries `delta: Record<string, unknown>`.                                                         |
 | `CUSTOM`               | Extension point. Carries `name` (string) and optional `value` (unknown).                                                    |
 | `RUN_FINISHED`         | Stream complete. Carries `runId` and `finishReason` (`'stop'` / `'length'` / `'content_filter'` / `'tool_calls'` / `null`). |
-| `RUN_ERROR`            | Error during stream. Carries optional `runId` and `error: { message, code? }`.                                              |
+| `RUN_ERROR`            | Error during stream. Carries `message`, optional `code` and `runId`; a nested `error: { message, code? }` copy is kept too. |
 
 **Typical event sequence for a text-only response:**
 
@@ -235,8 +239,10 @@ no helper, no cast:
 import { chat } from '@tanstack/ai'
 import { openaiText } from '@tanstack/ai-openai'
 
+const messages = [{ role: 'user' as const, content: 'Hello' }]
+
 const stream = chat({
-  adapter: openaiText('gpt-5.2'),
+  adapter: openaiText('gpt-5.6'),
   messages,
 })
 
@@ -284,7 +290,7 @@ causing events to arrive in batches instead of streaming token-by-token.
 
 Fix: Set proxy-bypass headers on the response.
 
-```typescript
+```typescript group=sse-response
 toServerSentEventsResponse(stream, {
   headers: {
     'X-Accel-Buffering': 'no', // nginx